Connectionist interaction information retrieval

Dominich, Sándor

doi:10.1016/s0306-4573(02)00046-8

Cited by 11 publications

(9 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In (Dominich, 2003), the author shows that term co-occurrence is exploited in the connectionist interaction retrieval model, and this can account for or contribute to its effectiveness.…”

Section: Introductionmentioning

confidence: 99%

A framework for understanding Latent Semantic Indexing (LSI) performance

Kontostathis

Pottenger

2006

Information Processing & Management

148

View full text Add to dashboard Cite

“…In (Dominich, 2003), the author shows that term co-occurrence is exploited in the connectionist interaction retrieval model, and this can account for or contribute to its effectiveness.…”

Section: Introductionmentioning

confidence: 99%

A framework for understanding Latent Semantic Indexing (LSI) performance

Kontostathis

Pottenger

2006

Information Processing & Management

148

View full text Add to dashboard Cite

“…This research should be complemented by the average-case analysis of these (and other) algorithms, coupled with the study of realistic models for the Web graph -an area of research which has seen much activity Pandurangan et al, 2002;Azar et al, 2001;Achlioptas et al, 2001;Kumar et al, 2000;Ruhl et al, 2001). Another issue of importance, under-explored so far in the IR literature, is a methodical analysis of the stability of the running times of the algorithms as their input is perturbed (see, for example, (Dominich and Tuza, 2003)). Stability of running times is especially important in the context of link-analyses on graphs of Web scale, as these algorithms demand considerable computational resources.…”

Section: Discussionmentioning

confidence: 99%

Rank-Stability and Rank-Similarity of Link-Based Web Ranking Algorithms in Authority-Connected Graphs

Lempel

Moran

2005

Inf Retrieval

View full text Add to dashboard Cite

Abstract. Web search algorithms that rank Web pages by examining the link structure of the Web are attractive from both theoretical and practical aspects. Today's prevailing link-based ranking algorithms rank Web pages by using the dominant eigenvector of certain matrices -like the co-citation matrix or variations thereof. Recent analyses of ranking algorithms have focused attention on the case where the corresponding matrices are irreducible, thus avoiding singularities of reducible matrices. Consequently, rank analysis has been concentrated on authority connected graphs, which are graphs whose co-citation matrix is irreducible (after deleting zero rows and columns). Such graphs conceptually correspond to thematically related collections, in which most pages pertain to a single, dominant topic of interest.A link-based search algorithm A is rank-stable if minor changes in the link structure of the input graph, which is usually a subgraph of the Web, do not affect the ranking it produces; algorithms A, B are rank-similar if they produce similar rankings. These concepts were introduced and studied recently for various existing search algorithms.This paper studies the rank-stability and rank-similarity of three link-based ranking algorithms -PageRank, HITS and SALSA -in authority connected graphs. For this class of graphs, we show that neither HITS nor PageRank is rank stable. We then show that HITS and PageRank are not rank similar on this class, nor is any of them rank similar to SALSA.

show abstract

“…As for the combination of evidence, there have been several different proposed approaches, based on bayesian networks (Croft and Turtle, 1989;Ribeiro-Neto and Muntz, 1996), or on the propagation of scores across the connections between documents (Dominich, 2002). All these approaches can be used for the combination of evidence, instead of Dempster-Shafer theory.…”

Section: Discussion Of the Proposed Modelmentioning

confidence: 99%

Dempster-Shafer Theory for a Query-Biased Combination of Evidence on the Web

Plachouras

Ounis

2005

Inf Retrieval

View full text Add to dashboard Cite

Abstract. This paper reports on a large-scale experiment for the evaluation of a formal query-biased combination of evidence mechanism. We use the DempsterShafer theory of evidence to combine optimally results obtained by content and link analyses on the Web. The query-biased mechanism is based on the query scope, a measure of the query specificity. The query scope is defined using a probabilistic propagation mechanism on top of the hierarchical structure of concepts provided by WordNet. We use two standard Web test collections and two different link analysis approaches. The results show that the proposed approach could improve the retrieval effectiveness.

show abstract

Connectionist interaction information retrieval

Cited by 11 publications

References 48 publications

A framework for understanding Latent Semantic Indexing (LSI) performance

A framework for understanding Latent Semantic Indexing (LSI) performance

Rank-Stability and Rank-Similarity of Link-Based Web Ranking Algorithms in Authority-Connected Graphs

Dempster-Shafer Theory for a Query-Biased Combination of Evidence on the Web

Contact Info

Product

Resources

About